Fast and effective kernels for relational learning from texts

Alessandro Moschitti, Fabio Massimo Zanzotto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Citations (Scopus)

Abstract

In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and the above kernels show the effectiveness and efficiency of our approach on two very important natural language tasks, Textual Entailment Recognition and Question Answering.

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
Pages649-656
Number of pages8
Volume227
DOIs
Publication statusPublished - 23 Aug 2007
Externally publishedYes
Event24th International Conference on Machine Learning, ICML 2007 - Corvalis, OR, United States
Duration: 20 Jun 200724 Jun 2007

Other

Other24th International Conference on Machine Learning, ICML 2007
CountryUnited States
CityCorvalis, OR
Period20/6/0724/6/07

Fingerprint

Syntactics
Dynamic programming
Support vector machines
Experiments

ASJC Scopus subject areas

  • Human-Computer Interaction

Cite this

Moschitti, A., & Zanzotto, F. M. (2007). Fast and effective kernels for relational learning from texts. In ACM International Conference Proceeding Series (Vol. 227, pp. 649-656) https://doi.org/10.1145/1273496.1273578

Fast and effective kernels for relational learning from texts. / Moschitti, Alessandro; Zanzotto, Fabio Massimo.

ACM International Conference Proceeding Series. Vol. 227 2007. p. 649-656.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Moschitti, A & Zanzotto, FM 2007, Fast and effective kernels for relational learning from texts. in ACM International Conference Proceeding Series. vol. 227, pp. 649-656, 24th International Conference on Machine Learning, ICML 2007, Corvalis, OR, United States, 20/6/07. https://doi.org/10.1145/1273496.1273578
Moschitti A, Zanzotto FM. Fast and effective kernels for relational learning from texts. In ACM International Conference Proceeding Series. Vol. 227. 2007. p. 649-656 https://doi.org/10.1145/1273496.1273578
Moschitti, Alessandro ; Zanzotto, Fabio Massimo. / Fast and effective kernels for relational learning from texts. ACM International Conference Proceeding Series. Vol. 227 2007. pp. 649-656
@inproceedings{661a4f01dbed46af8d712d7ae68dbb7b,
title = "Fast and effective kernels for relational learning from texts",
abstract = "In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and the above kernels show the effectiveness and efficiency of our approach on two very important natural language tasks, Textual Entailment Recognition and Question Answering.",
author = "Alessandro Moschitti and Zanzotto, {Fabio Massimo}",
year = "2007",
month = "8",
day = "23",
doi = "10.1145/1273496.1273578",
language = "English",
volume = "227",
pages = "649--656",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - Fast and effective kernels for relational learning from texts

AU - Moschitti, Alessandro

AU - Zanzotto, Fabio Massimo

PY - 2007/8/23

Y1 - 2007/8/23

N2 - In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and the above kernels show the effectiveness and efficiency of our approach on two very important natural language tasks, Textual Entailment Recognition and Question Answering.

AB - In this paper, we define a family of syntactic kernels for automatic relational learning from pairs of natural language sentences. We provide an efficient computation of such models by optimizing the dynamic programming algorithm of the kernel evaluation. Experiments with Support Vector Machines and the above kernels show the effectiveness and efficiency of our approach on two very important natural language tasks, Textual Entailment Recognition and Question Answering.

UR - http://www.scopus.com/inward/record.url?scp=34547970260&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547970260&partnerID=8YFLogxK

U2 - 10.1145/1273496.1273578

DO - 10.1145/1273496.1273578

M3 - Conference contribution

VL - 227

SP - 649

EP - 656

BT - ACM International Conference Proceeding Series

ER -